Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 391,369 indexed, measured the same four ways as everything else here.
Set up, verify, or uninstall talkback-mcp — connect AI assistants to Ableton Live via MCP. Use when the user wants to install, configure, troubleshoot, check, or remove talkback, or mentions connecting to Ableton.
Mutation testing patterns for Python using mutmut. Use when analyzing Python code to find weak or missing tests, verifying pytest effectiveness, strengthening Python test suites, or validating TDD workflows in Python projects.
Transform verbose markdown skills/commands into deterministic skflow scripts. Analyzes each step, classifies it as a shell command (sh), LLM judgment (ask), user interaction (askUser), or terminal state (done), then generates a compiled state-machine script that only yields to the LLM when judgment is needed.
A decision guide for choosing a university major after China’s national college entrance exam, known as the gaokao. It is based on analysis of more than 200 publicly shared teaching videos by Zhang Xuefeng.
Run Aperture Lab F-Stop on imported public trajectories, prepare review artifacts, compare disagreements, and propose bounded semantic-layer improvements under strict replay gates.
Complete Valyu API toolkit for AI agents. Use this skill when asked to perform real-time search across web, academic, medical, transportation, financial sources, content extraction from URLs, AI-powered answers with citations, or comprehensive deep research reports.
Control the VS Code Debugger (DAP) via CLI commands using mcp-debug-tools. Use when debugging, setting breakpoints, stepping through code, or inspecting variables.
Given a YouTube URL, fetch its transcript and extract atomic notes into an Obsidian vault. Use when handed a YouTube link to mine for ideas, or asked to "turn this video into atomic notes / atoms".
Create visual diagrams as Excalidraw files (.excalidraw) that ARGUE visually — process flowcharts, system architecture & data pipeline diagrams, sequence/timeline/lifecycle diagrams, mindmaps/org charts/hierarchy trees/entity-relationship (ER) diagrams. Use this skill when the user wants to "draw a diagram", "make a…
Sample, evaluate, and post-train Inkling and Inkling-Small from Pi. Use when the user mentions Inkling, tml-renderers, TMLv0, thinking effort, Inkling-Small, or Inkling audio/images. Load before writing Inkling training or eval code.
This skill should be used when developing desktop/web applications with Flet; encountering Flet 1.0+ version compatibility issues; migrating from Flet 0.x to 1.0+; encountering API errors with Tabs/Badge/Radio/BorderRadius controls; needing guidance on Flet animations, async operations, or layouts. Covers Flet 0.82.0+…
A task-execution procedure for an AI agent, written in Chinese, that emphasizes understanding the goal, confirming the task, completing all steps, checking the result, and delivering it. It also requires the agent to reveal assumptions and constraints.
This document defines logical sequences of commands that work together to accomplish common workflows. These sequences can be run manually or automated via scheduled jobs.
Compress images, long prompts, conversations, and RAG documents locally via Ollama before consuming LLM tokens. Reduces token usage by 80% on images and 85% on text. Use proactively when: the user uploads images, processes long context, works with multiple RAG sources, or when approaching token limits.
Monitor Facebook groups for new posts using Playwright browser automation with stealth mode and persistent login session. Scrapes group feed, tracks seen posts, reports only new ones. Captures a single stitched "feed strip" screenshot (viewport scroll + Pillow stitch) for efficient LLM vision analysis — one image…
Name: skillmaxxer-3000 Purpose: Intelligently architect Claude Skills with appropriate structure based on purpose and requirements Type: Meta-skill (builds other skills) Status: Production Ready Version: 4.0 Archetype: Complex/Interview (this skill uses its own framework).
Memoria Persistente Tienes acceso a una base de datos de memoria persistente.
★not rated 25 8mo agoA0 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: